AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Improving Semantic Embedding Consistency by Metric Learning for Zero-Shot Classiffication

Maxime Bucher, Stéphane Herbin, Frédéric Jurie

ECCV 2016 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 198 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the learned Mahalanobis metric (instead of Euclidean distance, W_A = identity) (ablation)zero-shot metric learning model (VGG) · aPascal&aYahoo ZSLaccuracy: 47.25 -> 53.15Improved
add the learned Mahalanobis metric (instead of Euclidean distance, W_A = identity) (ablation)zero-shot metric learning model (VGG) · AwA ZSLaccuracy: 73.81 -> 77.32Improved
add the learned Mahalanobis metric (instead of Euclidean distance, W_A = identity) (ablation)zero-shot metric learning model (VGG) · CUB-200-2011 ZSLaccuracy: 33.87 -> 43.29Improved
add the learned Mahalanobis metric (instead of Euclidean distance, W_A = identity) (ablation)zero-shot metric learning model (VGG) · SUN Attributes ZSLaccuracy: 74.91 -> 84.41Improved
add the attribute prediction term to the criterion (ablation)zero-shot metric learning model (VGG) · aPascal&aYahoo ZSLaccuracy: 48.47 -> 53.15Improved
add the attribute prediction term to the criterion (ablation)zero-shot metric learning model (VGG) · AwA ZSLaccuracy: 75.69 -> 77.32Improved
add the attribute prediction term to the criterion (ablation)zero-shot metric learning model (VGG) · CUB-200-2011 ZSLaccuracy: 38.35 -> 43.29Improved
add the attribute prediction term to the criterion (ablation)zero-shot metric learning model (VGG) · SUN Attributes ZSLaccuracy: 79.21 -> 84.41Improved
use VGG-VeryDeep-19 features instead of AlexNet featureszero-shot metric learning model · aPascal&aYahoo ZSLaccuracy: 46.14 -> 53.15Improved
use VGG-VeryDeep-19 features instead of AlexNet featureszero-shot metric learning model · CUB-200-2011 ZSLaccuracy: 41.98 -> 43.29Improved
use VGG-VeryDeep-19 features instead of AlexNet featureszero-shot metric learning model · SUN Attributes ZSLaccuracy: 75.48 -> 84.41Improved
add a few annotated examples of unseen classes and fine-tune (few-shot)zero-shot metric learning model · ZSL datasets (few-shot)accuracyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy